Difference between revisions of "Optimizer"

From
Jump to: navigation, search
m
m
Line 18: Line 18:
  
 
* [[AI Solver]] ... [[Algorithms]] ... [[Algorithm Administration|Administration]] ... [[Model Search]] ... [[Discriminative vs. Generative]] ... [[Optimizer]] ... [[Train, Validate, and Test]]
 
* [[AI Solver]] ... [[Algorithms]] ... [[Algorithm Administration|Administration]] ... [[Model Search]] ... [[Discriminative vs. Generative]] ... [[Optimizer]] ... [[Train, Validate, and Test]]
* [[Loss]] Functions
+
* [[Backpropagation]] ... [[Feed Forward Neural Network (FF or FFNN)|FFNN]] ... [[Forward-Forward]] ... [[Activation Functions]] ...[[Softmax]] ... [[Loss]] ... [[Boosting]] ... [[Gradient Descent Optimization & Challenges|Gradient Descent]] ... [[Algorithm Administration#Hyperparameter|Hyperparameter]] ... [[Manifold Hypothesis]] ... [[Principal Component Analysis (PCA)|PCA]]
* [[Activation Functions]]
 
* [[Gradient Descent Optimization & Challenges]]
 
 
* [[Objective vs. Cost vs. Loss vs. Error Function]]
 
* [[Objective vs. Cost vs. Loss vs. Error Function]]
 
* [http://www.tensorflow.org/api_guides/python/train TensorFlow Training Classes Python API]  
 
* [http://www.tensorflow.org/api_guides/python/train TensorFlow Training Classes Python API]  

Revision as of 21:04, 11 July 2023

YouTube search... ...Google search

There are many options for optimizer in TensorFlow. Optimizers are the tool to minimise loss between prediction and real value. There are many different weights a model could learn, and brute-force testing every one would take forever. Instead, an optimizer is chosen which evaluates the loss value, and smartly updates the weights. Click here For a list of Keras optimizer functions. Optimizer is one of the two parameters required to compile a model...



model.compile(optimizer='sgd'. loss='mean_squared_error')


Genetic Algorithm Optimization